© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 30371
    Prev
    Next
    INDEX
    Explanations

    CP or cp abbreviation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EN
    2.42
    ﻭ
    1.94
    Oui
    1.93
    ítás
    1.88
    lt
    1.88
    larıyla
    1.82
    া
    1.80
    throughput
    1.78
    bial
    1.77
    OFF
    1.75
    POSITIVE LOGITS
    ف
    3.22
    kę
    2.92
    та
    2.67
    ką
    2.66
    ください
    2.56
    ك
    2.52
    های
    2.38
    માં
    2.27
    할
    2.25
     rumors
    2.19
    Activations Density 0.005%

    No Known Activations